Featured Publications

Reinforcement learning in surgery

Patients and physicians make essential decisions regarding diagnostic and therapeutic interventions. These actions should be performed or deferred under time constraints and uncertainty regarding patients’ diagnoses and predicted response to treatment. This may lead to cognitive and judgment errors.

diagram showing reinforcement learning framework and challenges in development of reinforcement learning models

Artificial intelligence in acute medicine: a call to action

As AI continues to transform healthcare, it is crucial to address the technical, ethical, and social challenges that arise. AI is evolving from a mere tool to an assistant, and potentially a colleague. Likewise, AI must adhere to the same ethical standards colleagues follow to ensure credibility and trust remains. Our literature review, led by Maurizio Cecconi, explores the importance of data standardization, real-time ICU networks, and education in integrating AI into acute medicine. By focusing on these areas, we aim to enhance patient outcomes and strengthen the trust between healthcare providers and patients. Join us in advocating for responsible AI practices that uphold integrity in clinical settings.

cecconi

Intraoperative hypotension and postoperative acute kidney injury: A systematic review

Intraoperative hypotension (IOH) is tied to costly postoperative complications, including acute kidney injury (AKI). Better IOH control in non-cardiac surgeries alone could reduce postoperative costs by $1.6 million annually for hospitals with 10,000 patients.

Despite its effectiveness, there is no clean consensus on safe intraoperative blood pressure levels that protect against AKI, leaving clinicals without standardized guidelines for managing hypotension during surgery. 

Our latest research delves into defining IOH thresholds to mitigate AKI risks, aiming to guide safer and more cost-effective surgical practices.

IOH